Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Article beginnings or titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attentive
    -0.07
    terminated
    -0.07
    _skill
    -0.07
    ).↵↵↵↵
    -0.06
    tube
    -0.06
     imaginable
    -0.06
    .Assign
    -0.06
    _met
    -0.06
    !↵↵
    -0.06
     использовать
    -0.06
    POSITIVE LOGITS
     Graham
    0.06
    .NoArgsConstructor
    0.06
     fait
    0.06
    (error
    0.06
    (im
    0.06
    edics
    0.06
     quadratic
    0.06
    (Integer
    0.06
    Northern
    0.06
    ्दर
    0.06
    Act Density 0.203%

    No Known Activations